© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 6814
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﺎ
    0.89
    Когда
    0.85
    Pokud
    0.84
    ܢܐ
    0.84
    кое
    0.82
    חה
    0.82
    Э
    0.82
    ﻓ
    0.82
    ﺄ
    0.81
    ﻗ
    0.80
    POSITIVE LOGITS
    oretically
    0.75
     heure
    0.71
     autre
    0.71
     method
    0.70
     vectorize
    0.68
     hardest
    0.67
     utilize
    0.66
     integrate
    0.64
     craindre
    0.64
     inhibit
    0.64
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.